Aquilion Exceed LB

The Aquilion Exceed LB (TSX‐202A/3) V10.9 is a computed tomography system designed for comprehensive whole-body imaging, now enhanced with AiCE‐i technology extended to cardiac applications. Its methodology leverages Deep Convolutional Neural Networks for superior noise reduction and image quality, and incorporates new Dual Energy imaging features and advanced artifact reduction techniques like SEMAR for improved diagnostic capabilities across a wider range of clinical scenarios.

The Aquilion Exceed LB (TSX‐202A/3) V10.9 with AiCE‐i is a whole-body multi-slice helical CT scanner designed to acquire and display cross-sectional volume data sets for various anatomical regions, including the head, facilitating specialized studies by trained physicians. A key feature is AiCE (Advanced Intelligent Clear-IQ Engine), an advanced noise reduction algorithm that employs Deep Convolutional Neural Network (DCNN) methods to improve image quality. This version expands the clinical use of AiCE to cardiac applications, in addition to its existing applications for abdomen, pelvis, lung, extremities, head, and inner ear imaging. This iteration of the device introduces several enhancements, including Dual Energy imaging capabilities, featuring the generation of Electron Density Maps and Effective Atomic Number Maps. It also implements SUREStart technology and Single Energy Metal Artifact Reduction (SEMAR) specifically for the XL scan field. Performance testing using phantoms demonstrated that the system achieves substantially equivalent or improved image quality metrics (such as Contrast-to-Noise Ratios, CT Number Accuracy, Modulation Transfer Function, and Low Contrast Detectability) compared to its predicate. Studies also confirmed precise electron density and effective atomic number accuracy with the Dual Energy features, and diagnostic quality for AiCE-reconstructed cardiac images was affirmed by a board-certified radiologist.

AI Regulatory Concerns

Powered by

Jev reads the full FDA letter and returns calibrated concern probabilities per regulatory category. These are AI estimates, not regulatory advice.

• Q1. How does the performance of AiCE-i in cardiac applications compare to other established noise reduction techniques in terms of specific image quality metrics like contrast-to-noise ratio and spatial resolution, particularly under varying patient sizes or heart rates?; What is the quantitative impact of the new Dual Energy features, specifically the Electron Density Map and Effective Atomic Number Map, on diagnostic accuracy or differentiation of tissue types in relevant clinical scenarios?; Are there comparative studies demonstrating the clinical benefits of applying Single Energy Metal Artifact Reduction (SEMAR) in the XL scan field, particularly for patients with large metallic implants?; What are the specific training datasets and validation methods used for the Deep Convolutional Neural Network in AiCE-i, especially for the newly added cardiac applications?; How does the integration of SUREStart in the XL scan field optimize contrast media timing and image quality for larger patients or extended scan ranges?